© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2824
    Prev
    Next
    INDEX
    Explanations

    keywords related to personal actions, roles, commitments, and decisions related to a specific aspect or event

    oai_token-act-pair · gpt-3.5-turbo

    references to someone's role or actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gr
    -0.66
    orks
    -0.62
     Bus
    -0.58
     Salv
    -0.58
     Ort
    -0.58
     Airl
    -0.57
    vier
    -0.57
     Brit
    -0.57
     Whitman
    -0.56
    unn
    -0.55
    POSITIVE LOGITS
     foray
    0.80
     brethren
    0.79
     wife
    0.79
     holdings
    0.78
     counterparts
    0.77
     subordinates
    0.77
     mates
    0.77
     portfolio
    0.75
     prowess
    0.75
    mates
    0.74
    Activations Density 0.571%

    No Known Activations